4 dépôts
Systems that dynamically provide relevant information and tools to enhance the operational context of AI agents.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Context Engineering. Refine with filters or upvote what's useful.
LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution. The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing
Augments operational context by dynamically injecting relevant data and tool access into agent prompts.
This project is an autonomous software development assistant and project management tool that utilizes a multi-agent orchestrator to automate complex workflows. It functions as an agentic framework designed to research, plan, execute, and verify software development tasks by coordinating specialized agents that manage context windows and system performance. The system distinguishes itself through a structured, interview-based requirement engineering phase that clarifies project objectives before initiating automated work. It employs atomic task decomposition to break goals into independent un
Maintains project-specific documentation and state files to provide high-quality context for automated operations.
Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated
Organizes project information into a hierarchy of global rules, architecture specs, and transient outputs to optimize agent context.
Ce projet est une collection de bases de connaissances standardisées et de modèles de compétences qui définissent des méthodologies professionnelles pour les praticiens de la gestion de produits et les agents d'intelligence artificielle. Il fournit un framework structuré de compétences professionnelles et de connaissances pour garantir un niveau cohérent de qualité de sortie à travers la découverte de produits, la stratégie et l'alignement des parties prenantes. Le dépôt se concentre sur des frameworks spécialisés pour la gestion de produits par modèles de langage de grande taille, incluant des directives pour évaluer la préparation à l'intelligence artificielle, l'ingénierie de contexte et l'orchestration de flux de travail multi-agents. Il utilise une structuration des connaissances basée sur le markdown pour guider les agents IA dans la production de livrables professionnels et d'analyses stratégiques plutôt que de sorties génériques. Le projet couvre un large éventail de capacités de gestion de produits, notamment l'analyse des métriques commerciales pour la santé opérationnelle, la découverte client et la validation d'hypothèses, et la planification stratégique de roadmap utilisant des modèles de priorisation. Il inclut également des frameworks pour la rédaction de documents de besoins produits et d'user stories, la cartographie de l'influence des parties prenantes et le coaching exécutif pour les transitions de leadership.
Implements systems for organizing domain knowledge and operational constraints into prompts to guide AI agent orchestration.